Image-to-Text
Transformers
Safetensors
English
vlm
text-generation
image-captioning
visual-question-answering
Instructions to use 4bit/uform-gen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 4bit/uform-gen with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-text", model="4bit/uform-gen")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("4bit/uform-gen", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download input-interior.jpg from 4bit/uform-gen: direct link, hf CLI and curl.
- Browser
- Download file 44.4 kB
-
https://huggingface.co/4bit/uform-gen/resolve/main/input-interior.jpg
- Command line
-
hf download hf://4bit/uform-gen/input-interior.jpg
-
curl -L -o input-interior.jpg https://huggingface.co/4bit/uform-gen/resolve/main/input-interior.jpg
44.4 kB
